Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    plumbing

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ----------↵↵
    -0.06
    ским
    -0.06
    ******
↵
    -0.06
    _FR
    -0.06
     bots
    -0.06
     Auf
    -0.06
    ICA
    -0.06
     alike
    -0.06
    Trump
    -0.06
     livro
    -0.06
    POSITIVE LOGITS
     '['
    0.07
     luc
    0.07
    ासन
    0.06
    符合
    0.06
    ichten
    0.06
     Lantern
    0.06
    OptionsItemSelected
    0.06
    riters
    0.06
    โรค
    0.06
    <<<<<<<
    0.06
    Act Density 0.024%

    No Known Activations